【正文】 kfrot cage defect: at f = nfcage where n is the number of harmonics. As the defect is smaller, the measured acceleration signal is more like a pulse than like a sine wave and the energy content decreases while the defect frequency increases in the spectrum. DATA MINING II TECHNIQUE OF DATA PROCESSING Band enveloping is the process of transforming a vibration signal with small superimposed disturbances into isolated disturbance information. The main reason for using an envelope of a signal is that one can detect developing defects like small cracks in a very early stage. The process of band enveloping consists of three steps: highpass filtering, rectification, and lowpass filtering. As the energy of a disturbance pared to the energy of the sine wave is very low then the pulse is hardly detectable in the frequency spectrum. The first step therefore is to use a highpass filter to filter out the (low frequency) sinusoidal ponent. The remaining signal contains only the repetitive disturbances. The signal then is rectified and passed through a low pass filter. The peak in the frequency spectrum then represents the defect frequency of the ponent that is defective. The pulses lose the high frequency ponents because of the lowpass filter. The repetition period however remains. DATA MINING III — DATA ANALYSIS Data analysis can be quite plicated. If the scope of analysis is restricted to bearings and the four identified possible defects as listed Section , then the procedure can be as follows. First the frequency spectrum is scanned for anomalies. If peaks are detected in this spectrum then the equations (5) till (8) can be used to identify the root cause. Knowing the root cause, for example outer ring problems, then the acquired signal level is pared to a data base identifying the seriousness of the defect(s) and determining a proper course of action. Part of the latter determination is based on mon ifthenelse structures enabling a structured (and automated) analysis of possible causes and future effects on operation. If more than one possible cause for a defect is known, for example a specific signal can identify a defect in a bearing but also in the sensor itself, then confidence factors have to be applied to ruleout the most possible cause. AN INTELLIGENT MAINTENANCE CONCEPT In this section a concept for the logistic control of an intelligent maintenance system is given. The maintenance concept is based on the predictive maintenance concept, using either statistics or the results of a detailed data analysis, which was introduced in Section 2. The technical layout of the maintenance system is based on the application of an automated maintenance trolley including a monitoring and servicing robot as discussed in Section 3. The data acquisition and mining techniques used were discussed in the previous section. MODEL In the logistic model a number of elements are detailed including: ? the belt conveyor itself, ? the bearings, ? the maintenance robot, ? the inspection requirements, ? the servicing aspects, ? and the data analysis. Belt conveyor In the model the belt conveyor can be specified in terms of its length and the idler pitches. The number of idlers then is calculated automatically assuming that the pitch is constant. It is assumed that a carrying idler has 3 rolls and a return idler 2. Each roll has two bearings, which have a minimum life length as specified by the roll and bearing manufacturer. The number of the rolls that fail before the minimum life length can be specified. As a standard this number is 10%. If on a system used rolls, instead of new rolls, are installed then the program accounts for this effect by allocating remaining life lengths to individual rolls. Bearings The life length of a specific bearing in a roll is allocated via a tabularized distribution. Under and upper limits can be specified assuming a uniform distribution (mi。 kfrot inner ring defect: at f = nfir 177。 the repair activity was not scheduled beforehand. ? predictive maintenance: condition based, . ponents are being monitored and when irregular factors are discovered, one waits until a maintenance opportunity arises。 the decision to maintain a ponent based on opportunities may or may not be triggered by the condition of a ponent. ? corrective maintenance: emergency based, . repairing when a ponent malfunctions。 it may be based on observed deterioration of ponents。引入新的策略；譬如，檢查和維修分開進(jìn)行（在某種情況下檢查可以是自動(dòng)化而人工進(jìn)行維修）。在一個(gè)卷筒壽命周期內(nèi)，應(yīng)用統(tǒng)計(jì)方法 來改善壽命評(píng)估。 引入低頻率的固定檢查周期（周期時(shí)間 ~100 天），并在期間使用靈活的檢測(cè)策略。 因此，給出一些建議： 然而在這種情況下，檢查數(shù)次和提早更換卷筒將明顯增加。如果了解了視察機(jī)器人的特征，那么，壽命估算（ 在段落 ）就可評(píng)估， d 和 f 的最佳設(shè)置參數(shù)也就可以選擇。 性能水平依靠精確的剩余壽命評(píng)估。 結(jié)論和建議 通過本文的給出的分析可得出結(jié)論，設(shè)置一個(gè)帶式輸送機(jī)自動(dòng)維護(hù)系統(tǒng)的技術(shù) 基于臺(tái)車的應(yīng)用。然而，每個(gè)周期的檢查次數(shù)幾乎減少 4 倍。一個(gè)靈活的檢查計(jì)劃，對(duì)提早更換卷筒 方面的系統(tǒng)的使用性能 不影響。人工操作的臺(tái)車代替臺(tái)車檢查數(shù)次和行走與 額外花費(fèi)只和電力和數(shù)據(jù)處理時(shí)間相比較起來，人工操作 是非常昂貴的 。 表 8 表明 ，縮短了檢驗(yàn)周期間隔 可 導(dǎo)致減少浪費(fèi) 。對(duì)比表 6 和表 7 可以得出增加巡查數(shù)次 和增加提早更換卷筒大約 10 天（第 9 欄 — 天與 天） （第 7 欄 3308 與 6011） 可以為減少后期更換卷筒的成本。 壽命估算安全系數(shù) 表 7 f= 時(shí)，偏差的不同取值與對(duì)應(yīng)的 結(jié)果 設(shè)置 周期 早期更換 晚期更換 d f 周期間隔 安全時(shí)間 檢查時(shí)間 平均時(shí)間 總 花費(fèi) % 早期 早期平均 % 晚期 晚期平均 30 30 60 6011 100% 0% 30 30 60 5876 100% 0% 30 30 60 5571 99% 1% 在第二次 一系列 模擬中 安全系數(shù)為 引入。然而，偏差為 0 這種情況在實(shí)際上沒有出現(xiàn)過，估算達(dá)不到理想化。從表 6 可以得出結(jié)論，壽命估算偏差對(duì)維修機(jī)器人的成功是至關(guān)重要的。浪費(fèi)：卷筒在壽命終點(diǎn)之前被更換的平均時(shí)間 實(shí)驗(yàn) 下面的實(shí)驗(yàn)已經(jīng)執(zhí)行： 偏差值 d ， ， 安全系數(shù)值 f ， 機(jī)器人周期間隔 30 天， 15 天 安全時(shí)間 等于周期間隔 檢查時(shí)間 是安全時(shí)間的兩倍 模擬結(jié)果 本節(jié)列出一系列模擬表現(xiàn)結(jié)果。在卷筒壽命和超時(shí)更換卷筒之間的平均時(shí)間 用兩個(gè)性能指標(biāo)總結(jié)表現(xiàn)： 在過早更換卷筒和卷筒壽命之間的平均時(shí)間 每個(gè)周期平均檢查數(shù)次 列出結(jié)果如下： 表 5 模擬設(shè)置 運(yùn)行長(zhǎng)度 3650 天 隨機(jī)取值 54321 性能 指標(biāo) 維修機(jī)器人的性能由兩個(gè)因素決定 。 表 3 機(jī)器人設(shè)置 速度 檢查設(shè)置時(shí)間 30 秒 檢查時(shí)間 60 秒 維修設(shè)置時(shí)間 20 秒 維修時(shí)間 240 秒 策略 機(jī)器人策略將在 段落討論，下面是對(duì)實(shí)驗(yàn)設(shè)置的總結(jié)